Neural Decoding of Robot-Assisted Gait during Rehabilitation after Stroke

AbstractObjectiveAdvancements in robot-assisted gait rehabilitation and brain-machine interfaces (BMI) may enhance stroke physiotherapy by engaging patients while providing information about robot-induced cortical adaptations. We investigate the feasibility of decoding walking from brain activity in stroke survivors during therapy using a powered exoskeleton integrated with an electroencephalography (EEG)-based BMI.DesignThe H2 powered exoskeleton was designed for overground gait training with actuated hip, knee and ankle joints. It was integrated with active-electrode EEG and evaluated in hemiparetic stroke survivors over 12 sessions/4 weeks. A continuous-time Kalman decoder operating on delta-band EEG was designed to estimate gait kinematics.ResultsFive chronic stroke patients completed the study with improvements in walking distance and speed training over 4 weeks, correlating with increased offline decoding accuracy. Accuracies of predicted joint angles improved with session and gait speed, suggesting an improved neural representation for gait, and the feasibility to design an EEG-based BMI to monitor brain activity or control a rehabilitative exoskeleton.ConclusionThe Kalman decoder showed increased accuracies as the longitudinal training intervention progressed in the stroke participants. These results demonstrate the feasibility of studying changes in patterns of neuroelectric cortical activity during post-stroke rehabilitation and represent the first step in developing a BMI for controlling powered exoskeletons. Objective Advancements in robot-assisted gait rehabilitation and brain-machine interfaces (BMI) may enhance stroke physiotherapy by engaging patients while providing information about robot-induced cortical adaptations. We investigate the feasibility of decoding walking from brain activity in stroke survivors during therapy using a powered exoskeleton integrated with an electroencephalography (EEG)-based BMI. Design The H2 powered exoskeleton was designed for overground gait training with actuated hip, knee and ankle joints. It was integrated with active-electrode EEG and evaluated in hemiparetic stroke survivors over 12 sessions/4 weeks. A continuous-time Kalman decoder operating on delta-band EEG was designed to estimate gait kinematics. Results Five chronic stroke patients completed the study with improvements in walking distance and speed training over 4 weeks, correlating with increased offline decoding accuracy. Accuracies of predicted joint angles improved with session and gait speed, suggesting an improved neural representation for gait, and the feasibility to design an EEG-based BMI to monitor brain activity or control a rehabilitative exoskeleton. Conclusion The Kalman decoder showed increased accuracies as the longitudinal training intervention progressed in the stroke participants. These results demonstrate the feasibility of studying changes in patterns of neuroelectric cortical activity during post-stroke rehabilitation and represent the first step in developing a BMI for controlling powered exoskeletons. Equal contributions, Magdo Bortole and Fangshi Zhu. Correspondence: Jose L Contreras- Vidal, Noninvasive Brain-Machine Interface Systems Laboratory, Department of Electrical and Computer Engineering, University of Houston, N308 Engineering Building I, 77204-4005 Houston, USA. School of Engineering, Tecnologico de Monterrey, Monterrey, Mexico. kcnathan@uh.edu Competing interests: The authors declare that they have no competing interests. Funding: This work has been partially supported by the Noninvasive Brain-Machine Interface Lab at the University of Houston, the Monterrey Institute of Technology, and the HYPER Project (Hybrid Neuroprosthetic and Neurorobotic Devices for Functional Compensation and Rehabilitation of Motor Disorders). Ministerio de Ciencia y Innovación, Spain (CSD2009 - 00067 CONSOLIDER INGENIO 2010). Copyright © 2018 Wolters Kluwer Health, Inc. All rights reserved.

from Rehabilitation via xlomafota13 on Inoreader http://ift.tt/2BQzRhF
via IFTTT